Local Multi-Head Channel Self-Attention for Facial Expression Recognition

Pecoraro, Roberto; Basile, Valerio; Bono, Viviana; Gallo, Sara

doi:10.48550/arxiv.2111.07224

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The author obtains the best accuracy of 76.40% 23 on RAF-DB with Tokens-to-Tokens ViT model and 77.33% on balanced FER2013 dataset with Mobile ViT. 24 The author in 25 used Local Head Channel (LHC) Self-attention in combination with a pre-trained ResNet34v2 trained on FER2013, as a backbone. The idea behind using local heads is that they work at a much lower dimension and they are efficient.…”

Section: Related Workmentioning

confidence: 99%

Improved face transformer model for facial emotion recognition in human-machine collaboration

Roka,

Rawat

2024

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications VI

View full text Add to dashboard Cite

With the spread of powerful AI models, human-machine interaction has improved rapidly. In this situation, recognizing facial expressions of human emotion is essential for successful human-machine collaboration/ teaming. While Convolutional Neural Network (CNN) models were widely used for facial emotion classification, Transformer-based models, known for excelling in NLP tasks, have demonstrated superior performance in areas like image classification, semantic segmentation, and object detection. This study investigates the effectiveness of using a transformer based model, the Face-transformer model a powerful tool for facial identification, that will be fine-tuned for the Facial Emotion Recognition (FER) challenge. We aim to modify the face transformer architecture to recognize emotional states from facial photos using the extensive facial emotion recognition datasets, opening the door for more natural and responsive machine interactions. Our initial findings suggest that the Face-Transformer model holds promise for bridging the gap between machine interpretability and human emotions, potentially paving the way for more natural and responsive human-computer interactions.

show abstract

Section: Related Workmentioning

confidence: 99%

Improved face transformer model for facial emotion recognition in human-machine collaboration

Roka,

Rawat

2024

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications VI

View full text Add to dashboard Cite

show abstract

“…Accuracy rate CNN [38] 72.16 ResNet [39] 72.4 VGGNet [40] 73.28 DeepEmotion [41] 70.02 SVM [42] 71.16 SE-Net50 [43] 72.7 LHC-Net [44] 74.42 ResNet18 64.8 The proposed model 72.7…”

Section: Modelmentioning

confidence: 99%

Facial Expression Recognition Based on Multi-Channel Attention Residual燦etwork

Shen¹,

Xu²

2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

For the problems of complex model structure and too many training parameters in facial expression recognition algorithms, we proposed a residual network structure with a multi-headed channel attention (MCA) module. The migration learning algorithm is used to pre-train the convolutional layer parameters and mitigate the overfitting caused by the insufficient number of training samples. The designed MCA module is integrated into the ResNet18 backbone network. The attention mechanism highlights important information and suppresses irrelevant information by assigning different coefficients or weights, and the multi-head structure focuses more on the local features of the pictures, which improves the efficiency of facial expression recognition. Experimental results demonstrate that the model proposed in this paper achieves excellent recognition results in Fer2013, CK+ and Jaffe datasets, with accuracy rates of 72.7%, 98.8% and 93.33%, respectively.

show abstract

Local Multi-Head Channel Self-Attention for Facial Expression Recognition

Cited by 2 publications

References 23 publications

Improved face transformer model for facial emotion recognition in human-machine collaboration

Improved face transformer model for facial emotion recognition in human-machine collaboration

Facial Expression Recognition Based on Multi-Channel Attention Residual燦etwork

Contact Info

Product

Resources

About